Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2022 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.9521. Min Range: -2.9521

Max Act: 2.9521. Min Act: -0.0000

Data Index: 281679 (C4 (Web Text))

Max Activating Token Index: 242

Text #1

Max Range: 2.9521. Min Range: -2.9521

Max Act: 2.7744. Min Act: -0.0000

Data Index: 569096 (C4 (Web Text))

Max Activating Token Index: 369

Text #2

Max Range: 2.9521. Min Range: -2.9521

Max Act: 2.7623. Min Act: -0.0001

Data Index: 193113 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 2.9521. Min Range: -2.9521

Max Act: 2.5815. Min Act: -0.0001

Data Index: 226470 (C4 (Web Text))

Max Activating Token Index: 396

Text #4

Max Range: 2.9521. Min Range: -2.9521

Max Act: 2.3418. Min Act: -0.0000

Data Index: 1019486 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 2.9521. Min Range: -2.9521

Max Act: 2.1207. Min Act: -0.0000

Data Index: 68787 (C4 (Web Text))

Max Activating Token Index: 709

Text #6

Max Range: 2.9521. Min Range: -2.9521

Max Act: 2.1774. Min Act: -0.0000

Data Index: 896287 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 2.9521. Min Range: -2.9521

Max Act: 2.1281. Min Act: -0.0000

Data Index: 1218991 (C4 (Web Text))

Max Activating Token Index: 148

Text #8

Max Range: 2.9521. Min Range: -2.9521

Max Act: 2.2376. Min Act: -0.0001

Data Index: 448087 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 2.9521. Min Range: -2.9521

Max Act: 2.3242. Min Act: -0.0001

Data Index: 269549 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 2.9521. Min Range: -2.9521

Max Act: 2.1059. Min Act: -0.0001

Data Index: 498295 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 2.9521. Min Range: -2.9521

Max Act: 2.0181. Min Act: -0.0000

Data Index: 5809 (C4 (Web Text))

Max Activating Token Index: 822

Text #12

Max Range: 2.9521. Min Range: -2.9521

Max Act: 1.9060. Min Act: -0.0000

Data Index: 963149 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 2.9521. Min Range: -2.9521

Max Act: 1.8829. Min Act: -0.0000

Data Index: 564510 (C4 (Web Text))

Max Activating Token Index: 934

Text #14

Max Range: 2.9521. Min Range: -2.9521

Max Act: 1.9572. Min Act: -0.0000

Data Index: 725397 (C4 (Web Text))

Max Activating Token Index: 112

Text #15

Max Range: 2.9521. Min Range: -2.9521

Max Act: 1.9337. Min Act: -0.0000

Data Index: 411217 (C4 (Web Text))

Max Activating Token Index: 844

Text #16

Max Range: 2.9521. Min Range: -2.9521

Max Act: 1.8120. Min Act: -0.0000

Data Index: 1333620 (C4 (Web Text))

Max Activating Token Index: 966

Text #17

Max Range: 2.9521. Min Range: -2.9521

Max Act: 1.8764. Min Act: -0.0001

Data Index: 17721 (C4 (Web Text))

Max Activating Token Index: 71

Text #18

Max Range: 2.9521. Min Range: -2.9521

Max Act: 1.9571. Min Act: -0.0001

Data Index: 1289246 (C4 (Web Text))

Max Activating Token Index: 855

Text #19

Max Range: 2.9521. Min Range: -2.9521

Max Act: 1.8377. Min Act: -0.0001

Data Index: 239036 (C4 (Web Text))

Max Activating Token Index: 517